{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:K7PZNDXVZEJCL5C426PZU6AG2Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6fb5cbd0dc75279714fd6213ed376031d47af854113dd4a9fecaebaf6e7ecbac","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-30T21:49:07Z","title_canon_sha256":"68b41c254f96e35b545006dae62c3d1a9d92d932163b3abd7f6f9b3f2485caf8"},"schema_version":"1.0","source":{"id":"1907.00477","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00477","created_at":"2026-07-05T00:28:50Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00477v2","created_at":"2026-07-05T00:28:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00477","created_at":"2026-07-05T00:28:50Z"},{"alias_kind":"pith_short_12","alias_value":"K7PZNDXVZEJC","created_at":"2026-07-05T00:28:50Z"},{"alias_kind":"pith_short_16","alias_value":"K7PZNDXVZEJCL5C4","created_at":"2026-07-05T00:28:50Z"},{"alias_kind":"pith_short_8","alias_value":"K7PZNDXV","created_at":"2026-07-05T00:28:50Z"}],"graph_snapshots":[{"event_id":"sha256:d11912f02b08aab345532a652046f02eb0bc98a7a947bb54857c074a8641d32f","target":"graph","created_at":"2026-07-05T00:28:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1907.00477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal learning allows us to leverage information from multiple sources (visual, acoustic and text), similar to our experience of the real world. However, it is currently unclear to what extent auxiliary modalities improve performance over unimodal models, and under what circumstances the auxiliary modalities are useful. We examine the utility of the auxiliary visual context in Multimodal Automatic Speech Recognition in adversarial settings, where we deprive the models from partial audio signal during inference time. Our experiments show that while MMASR models show significant gains over ","authors_text":"Florian Metze, Ramon Sanabria, Tejas Srinivasan","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-30T21:49:07Z","title":"Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00477","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3ace19d60ceba1fc7c08491fb2cf88f39c9c52819524c6c0f91ff8f694298a05","target":"record","created_at":"2026-07-05T00:28:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6fb5cbd0dc75279714fd6213ed376031d47af854113dd4a9fecaebaf6e7ecbac","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-30T21:49:07Z","title_canon_sha256":"68b41c254f96e35b545006dae62c3d1a9d92d932163b3abd7f6f9b3f2485caf8"},"schema_version":"1.0","source":{"id":"1907.00477","kind":"arxiv","version":2}},"canonical_sha256":"57df968ef5c91225f45cd79f9a7806d67f3a4c309c2d1777717df4504df951a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57df968ef5c91225f45cd79f9a7806d67f3a4c309c2d1777717df4504df951a3","first_computed_at":"2026-07-05T00:28:50.034393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:50.034393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aDFqjvQYoffVBuWloMUSugDt+ijltv785cBtNyyHGdXyuIjKDbK+7+yMwuma5LTSZVCtsNLi+5ncZUzVnOoJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:50.034898Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.00477","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ace19d60ceba1fc7c08491fb2cf88f39c9c52819524c6c0f91ff8f694298a05","sha256:d11912f02b08aab345532a652046f02eb0bc98a7a947bb54857c074a8641d32f"],"state_sha256":"2ffdbbd395ff9f8c080daef86effb3da5dd60a998d798aa9cb30be9d2a463a49"}